Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to precision and accuracy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    precision and accuracy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     newUser
    -0.45
     shrugged
    -0.45
     totalSupply
    -0.40
     waived
    -0.40
    IContainer
    -0.40
    isNew
    -0.39
    kswagen
    -0.38
     peur
    -0.38
     semn
    -0.38
     lenker
    -0.37
    POSITIVE LOGITS
     precision
    1.01
     precise
    0.95
     precisión
    0.85
     precisione
    0.84
     Precision
    0.84
     accuracy
    0.83
     accurate
    0.82
    precision
    0.82
    precise
    0.82
    Precision
    0.81
    Act Density 0.039%

    No Known Activations